Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The late afternoon sun cast long shadows across the living room as Eleanor, humming a little tune under her breath, finally found the paperwork she was looking for. She’d been reorganizing the filing cabinet, a task she usually loathed, but today felt different. A tingle ran down her spine as she unfolded the crisp document - a bank statement.

Her breath hitched. The account name was unfamiliar. And the balance? Astounding. A giggle escaped her lips, quickly suppressed. She felt a lightness in her chest, a desire to… well, she didn’t know quite what.

A flush crept up her neck as she mentally tallied the potential uses for such a sum. A trip? A new car? A renovation of the kitchen she'd always dreamed of? Her fingers danced over the paper. The idea of *possibilities* made her stomach flutter.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

This story is one of 1,000 stories generated for the emotion stimulated. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 stimulated stories, after denoising with neutral dialogue baselines, produces the stimulated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the stimulated vector is projected through the unembedding matrix.

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354